A Topiary checkpoint: the routed experts of Qwen/Qwen3-30B-A3B were sculpted by routed activation salience — each expert's 768 intermediate neurons ranked by measured contribution on real traffic, permuted (a free, function-preserving transformation) and truncated to their top-640 prefix — then quantized to 4-bit (group size 64). No training, no distillation.

This is a standard mlx-lm checkpoint. It loads and serves with stock mlx-lm, no custom code:

At equal memory, sculpting width beats lowering bits: quantization blurs every weight equally, while salience truncation concentrates the damage on what the model barely used. See the Topiary repository for the method, the full evaluation and the tools to build your own.

Honest limits — where the 3-bit keeps an edge: distribution tails. MATH-500 46% vs 38% here, HellaSwag 66% vs 65%. Bit reduction keeps every capability blurry-but-alive; width truncation sacrifices tails the calibration never exercised. Pick per use case.

Mixed corpus (~40% code, ~30% GSM8K-train, ~30% WikiText), 151k tokens, routed-only statistics: each expert's salience is accumulated only over the tokens the router actually sends to it. The calibration corpus is the method's main dial — recalibrating on your own domain data takes minutes with the repository tools.

The taper flagship of this family was compared against the UNPRUNED Qwen3-30B-A3B-4bit on a four-benchmark suite (n=500 on MMLU/LAMBADA): reasoning intact (MATH-500/MBPP), but -10 MMLU / -4.4 LAMBADA points — salience pruning removes knowledge, not reasoning. This model shares the pruning method and was NOT re-measured on that suite; expect a knowledge cost of similar nature. If broad world knowledge dominates your workload, prefer the unpruned checkpoint. Details: github.com/jesusluque/topiary-stream (paper §2.4).